Hikvision Acusense Analytics Tested

By: Rob Kilpatrick, Published on Sep 23, 2019

Hikvision touts "The Magic Behind It All" in their new Acusense line are 'deep learning algorithms' inside these cameras and recorders. But how well do these new models work?

free image1

We bought and tested the Hikvision DS-2CD2346G1-I/SL camera and DS-7608NXI-I2/8P/4S NVR for over three weeks, examining:

  • False alert performance: What did and did not cause false alerts?
  • Intrusion detection accuracy: Did it miss valid people or vehicles in the scene in multiple conditions?
  • Ease of setup: How difficult or time-consuming was setup and optimization?
  • Vs. competitive analytics: How did DeepinView compare to AI analytics such as Dahua Analytics+ and Wyze Cam and camera analytics from our IP Camera Analytics Shootout?
  • What components does it use? Ambarella, Huawei, Intel, NVIDIA, others?
  • How well does it integrate with major VMSes?

Readers should also see our tests of Hikvision's DeepinView AI analytics camera and DeepinMind NVR.

********* ***** "*** ***** Behind ** ***" ** their *********** ******* '**** ******** **********' inside ***** ******* *** recorders. *** *** **** do ***** *** ****** work?

free image1

** ****** *** ****** the********* **-*********-*/******** *****-*******-**/**/** ****** **** ***** *****, examining:

  • ***** ***** ***********: **** did *** *** *** cause ***** ******?
  • ********* ********* ********: *** it **** ***** ****** or ******** ** *** scene ** ******** **********?
  • **** ** *****: *** difficult ** ****-********* *** setup *** ************?
  • **. *********** *********: *** did ********** ******* ** AI ********* **** ******* *********+******* ****** ****** ********* **** our** ****** ********* ********?
  • **** ********** **** ** use? *********, ******, *****, NVIDIA, ******?
  • *** **** **** ** integrate **** ***** *****?

******* ****** **** *** our ***** ** *********'*********** ** ********* ******************* ***.

[***************]

*******

**** *** ****** ** three ***** ** *******, Hikvision's ******** *** ******* positives:

  • ** ***** ****** ** Most ******* *******:******** ******* **** ** swaying ********/*******, ******* **** produced, *** **** ******** on *** **** ** the ****** *** *** trigger ***** ******.
  • ** ***** ****** ** Most ****** ****** *******:****** ****** ******* ** false ****** **** ** drastic ***** *******, ******* moving ******* *** *****, and ****** ******* ** and *** **** ******* throughout *******.
  • ******** ********* ** ****** Walking ******* ** ********:******** *** *** **** people ******* ******* ** crawling ******* *** ***** during *******, *** ** night.

*******, ** ******* **** significant ****** **** ***************** and ***** ******:

  • ****** ********** ** ********:****** ******* ******* *** scene **** ********* ********** as ********, **** ***** when ******** **** ** the **********. **** ***** result ** ****** ***** completely ****** ** ***** turn *** ******* ****** indoors, *** ********* ** detect ********.
  • ***** ****** ** *******:***** *** ***** ******* (ranging **** **** ******* deer) ******* ******* *** scene ********* ******** ***** alerts, ********** ** ******** used. ******* **** **** often ********** ** ********.
  • ***** ****** ** ****** Cars:****** **** ** *** scene **** ********* **** as ****** ******* **** passing ****** ****** ******* in ********.
  • ******** ***** ****** ** Sunlight ******* *******:******** ******* * ***** window *** **** ****** false ****** **** ** moving ******* ** *** scene.
  • ****** *** ******** ******* Through *****:****** ******* ******* *** scene **** ****** **********, day *** *****, ******* and ***.

Hikvision ********

**** **** ********* *** given *** *********** ** review ******* ****** ******* but *** *** ***** any *********** *** ******** changes ** ******* *********. They ******* *** **** Acusense ******* ****** **** in *********** **** ******** NVRs, *** ** *** tests ** *** ** difference ** *********** ******* Acusense *******' ** ***** detection *** ******** ******* used ** *********** **** the ***.

Settings ******* ****** ** *** ******

** *** ******, ** adjusted ******** ** *** if ********* *********** ********, but ***** **** ******* settings ******** *** **** results. ** *********'* ********* analytics, ********* ********, *** only ******** *********** *** threshold (**** ****** ** in ***** ****** **********) and *********** ("**** ** the ****** ***** *** trigger *****"). ******* ** these ******** ********** ***** alerts.

Vs. ***** *********+

*****'* *********+****** ************ ********* ********, with ** ***** ****** on ******* ** ****** which ********* *** ********* Acusense. ************* *** **** is *******, *********** **** requiring * **** ** be *** *** ****** and/or ******* ********* ********.

Vs. **** **

****'* **** ** ****** detection*********** ********, ******** *******, foliage, ******, *******, *** other *******. *******, **** has **** ***-******** *********** which **** ** ********** for ********** *** *** it ***** *********** ** third ***** ***.

Vs. ******** *** ***** ***

********'* ****-******** ***************** ***(*** ******* ** ***** ****** ********* ********) **** ************ ********, ignoring ****** **** ******* and ***** *** *** not ****** **** *** same ************** ****** ** Acusense.

Vs. ********* ******** ********* *** ***

******** ** *********'* ******** Intrusion *********, ******** *********** is ******* ******, ********* more ***** ****** **** more *******, ********* ******* and ******, **** ****** on *******, ***. *********** is *********** ****** **** standard ***, ***** ******* on *********** *** ***** change, ********* *** *** limited ** *** ****** false ***** ******* *****, without ************** ******* ******, vehicles, ** ***** *******.

*******

*** ********* **-*********-*/** *** be ***** ****** ***~$*** ******** *** **-*******-**/**/** (* channel/8 ***/* ******** *********) sells ***~$*** *** ******.

People ******** ******* *******/********, *** *******

******** ******** ****** ******* upright ********** ******* **** no ****** ****** *** detection ***** *** *** night:

******** ******** **** **** detected ** *** ***** using ******* ********.

Running ****** ******

*******, ****** ******* ******* the ***** **** ****** completely. ** ******** ******* improved **** *********.

Running-Subjects-Not-Detected

People ********** ************* ** ********

****** ******* ******* *** scene, ****** ** *** foreground/walking ****** *** ****** were ********** ********** ** vehicles. **** ***** **** to ********** ****** ********** if ***** ****** ** detect **** ******.

False ****** ** *******

******** ********** ******* ** both ***** *** ***** animals ** *** ***** of ****. ******* **** most ***** ********** ** vehicles, *** ********* ********** as ***** **** ******* toward *** ******.

False ****** ** ****** ****

****** *******, ******** ******* on ****** ******** **** cloud ******** ** ***** light ******* ********, **** though *** ******* *** not ****. ***** *********+ also ******** **** **** issue, ****** ** **** not **** ** ** other *********.

parked vehicle alert

False ****** ** ********

** *** *****, ******** alerted ** ******** ********* on *** ***** **** the ***** ****/*******. **** occurred *-* ***** *** day ** *** ****** of *** ****.

No ***** ****** **** *******, *******, ** ************

********, ******** ******* ***** alerts **** ****** ******* such ** ******* ******* and *** ******* **** produce, **** *****.

No-False-Alerts-On-Foliage_Shadows-Outdoors

******** **** ******* *** of *** **** ****** sources ** ***** ******, heavy **** *** **** dripping **** *** ****.

No-False-Alerts-On-Rain_Droplets

No ****** ***** ****** ** ****** ** *******

****** ******* ******** ******* all ****** ****** ***** alerts **** ** ******* light ******* ** *** scene, ***** *****.

******* **** ****** ****** through *** ***** **** also *******.

Detection ********

** *** *****, ******** reliably ******** ** ~***' distance, ~** *** ** the *** **-*********-*/** ****** we ******. ***** *** requirements *** ***, ********** to ***** ** ********, and ***** *************'* *** ********* *********, ***** ******** ****** double *** *** *** detection *** *** **** more ***** ***** ******.

Simple *****

***** ** *** **** step **** *********'* ****** intrusion ********* *****, **** requiring *** **** ** choose ** ****** ***/** vehicles ****** ** ******** in *** *****:

VMS ***********

******** ****** ****** ********* to*********'* ******* ********* *********** ***** ***** ***. These ****** **** ********* in ** ******* *** Milestone ********, *** *** analytics **** *** ********* in ***********, ******** ******* Center, ** ******* ******** Center.

Camera ********: ********* *** ******** ***** ****

*** ********* **-*********-*/** ****** uses ** ********* ***-*-**-** system ** ****, * common *** *** ***** cost ******.

Ambarella S3L System On Chip

*******, ** **** ******** a******** ************ ********** **** (***), unlike **** ***** **/******** models ***** **** ******** only * ****** ****. This ** ********' ******* generation, ******** ** **** (see *** ******:***** ******** ******* ***** Surveillance ******).

Versions ****

*** ********* ******** **** used ****** *******:

  • ********* **-*********-*/**: **.*.** ***** 181213
  • **-*******-**/**/**: **.*.** ***** ******

Comments (24)

** ***** **** ***** is * *** ** turn *** *** ********* for ******* ** ***** so ** ** **** I ***** **** ***** be ******* *** ***** in * ***** ******* scene. *******, **** ***** leads ** ** ******* they *** ** ***** the **** ** ** object ** *** ***** to ************* ******* ***** or ****?

* ********** **** ** know ** ***** ** a *** ** ** mall!

*** ****, ** * set ** * ****** in **** ******* ** production, * ***** ****** not **** ******* *** "vehicle" ********* ***. ****'* exactly *** *******. ** we *** ******* **** person ********* ** **** scene, ** ***** **** missed * *********** ****** of ********. **** ****** aren't ******** ** ***.

** **** ***** ** to ******* **** **** are *** ***** *** kind ** **** ****** classification, **** ******** **** today **** ***/*** *********. Kind ** ******* ***** their *** ** *** Movidius ****, **** **** test **** ** *** seem ** ** ***** utilizing *** ************.

**'** ***** * ******* comparing ******** ** *********'* standard ********* *** ***:

Vs. ********* ******** ********* *** ***

******** ***********'* ******** ********* *********, ******** *********** ** clearly ******, ********* **** false ****** **** **** sources, ********* ******* *** lights, **** ****** ** animals, ***. *********** ** drastically ****** **** ******** VMD, ***** ******* ** practically *** ***** ******, including *** *** ******* to *** ****** ***** alert ******* *****, ******* discriminating ******* ******, ********, or ***** *******.

* *** ******* *** drastic *********** ** ********* and ******* ******* ******* compared ** *** ******** generation. **** ******, ***** you!

* **** **** **** improve *** ********* ********** in *** ****** ** versions

******* **** ********* ********** as *****...*******, ****** ******* through *** ***** **** missed **********. ** ******** changes ******** **** *********.

******: **** *****?

******: *** ** *****, turned *** ** ** a ***. *********, *******...

*** *****. *** **** if *** **** ** try ****, *** ** you **** **** ***** happen ** *** ***** sensitivity ** ** **, or ***? **** ******* if **** ***** **** the ****** ***** **** moving *******.

**** * ****** **** I *** ****** *********** and ********* ** *** and *** ** ***** while * *** *******, even ****** ** ** max ******'* ******* ** alarm, ** *** *** even **** * ******** box ****** **.

...*** ** ***** ***** I *** *******, **** having ** ** *** wouldn't ******* ** *****, it *** *** **** draw * ******** *** around **.

***: *** *** *** that?

**: *** ****?

SoC: If I knew “what”, I wouldn’t need you. Something just went flying by...

**: *** **** **** blurred ****** ** *****. I **** ** ****. It’s **** ***. ******, out ** *****, *** of ****, *****?

***: **** *’* ***** send ** ***** ******, the **** ****** ** notified!

**: *** **** *** you ***** ** *** it ** **** ****, a *******, * ***, maybe * **** *****?

***: ***, ***’** ***** those *** ******* *****. You *** *** *****?

AI: Yeah, keep your trap shut. Remember, if faced with the choice of false negative vs. false positive, ALWAYS choose false negative. If you missed it, they probably will too; nobody’s the wiser. On the other hand, calling out “heavy snow” in July will just put us on the cover of IPVM, again!

***: ***’** ** *****!

****** *** *** *********** Rob.

** **** - *** of *** ****** ***** triggers ** ******* ** night. ** *** ***** figure *** *** ** test *** **** ** would ** **** *******.

******, **** *** ******* different *****.

***** ** *** ***** I ** *** **********.
********* *** ********, *****?
*** ***** ******** **** to ** ***** *** different **********.
*** *** **** *** do * **** *** on ******* **?
** ** *** ****** use *** ** *** box ****?

*** *** **** *** do * **** *** on ******* **?

** ***** ********** **** Hikvision ********** ********** **** test *** ************ ***** feedback *** ***********. ***** will ****** *** ****** with *******.

******. * ****** *** do *** **** **** other *************, ** *** do ****** ******** **** scene ** *****.

*** *******, **'** ***** two ******** ** *** report. ** ** ***** tests, ** ******* *** to ********* *** ******* and *********** ** ********** the *********. ** **** perform *** *** ******** changes ** *** **** effects **** **** (** this ****, ******* ** none).

Hikvision ********

**** **** ********* *** given *** *********** ** review ******* ****** ******* but *** *** ***** any *********** *** ******** changes ** ******* *********. They ******* *** **** Acusense ******* ****** **** in *********** **** ******** NVRs, *** ** *** tests ** *** ** difference ** *********** ******* Acusense *******' ** ***** detection *** ******** ******* used ** *********** **** the ***.

Settings ******* ****** ** *** ******

** *** ******, ** adjusted ******** ** *** if ********* *********** ********, but ***** **** ******* settings ******** *** **** results. ** *********'* ********* analytics, ********* ********, *** only ******** *********** *** threshold (**** ****** ** in ***** ****** **********) and *********** ("**** ** the ****** ***** *** trigger *****"). ******* ** these ******** ********** ***** alerts.

** *****,

** ************* ** ***'* Acusense ** *** *** get ***** ********* **-***** the ****** ** **** as ***** **** *** NVR. *** *** **** work *** ********* ** ordinary ****** *****, ***** Acusense ******* **** ******* the ********* ** ***-******** NVRs ** **** ******* through ** ***** ************.

** **** *******? ** so *'* ******** ** picking ** *** ** the ******** **** ** replace *** *** ** have ** *** **** which *** ******* ** cameras **** *** ***** analytics. ********?

***, ***, **** ** correct, *** ******** *** analytics **** **** **** third ***** ****** ******* and ******* ****** *** vehicle ******. *** ******** cameras **** **** ***** notifications ** ***-******** **** but ***'* ******* *** classification.

****** **** **** *** the *************!

*****,

* ******* ***** ***** be * **** ** the "Vs. **** **" section of the article. You mentioned "Axis Perimeter Defender" should that be Acusense instead?

******,

***, *** *** *****. I've ***** ****, ****** for ******** ** ***!

You **** :

Detection ********

** *** *****, ******** reliably ******** ** ~***' distance, ~** *** ** the *** **-*********-*/** ****** we ******

********:

*** ****** ******* *** lens **** ** *** test? *.***, *** ** 8mm?

** *** ** ***' - **'* *.***

**** ** *******, ** used * *.*** *** the ****.

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports

Video Surveillance 101 Course Opened on Dec 12, 2019
IPVM is adding a Video Surveillance 101 course, designed to help those new to the industry to quickly understand the most important terms,...
Hikvision DS 2nd Gen Intercom Tested on Dec 12, 2019
With its newest IP intercom, Hikvision proclaims users can 'get full control over an entrance' regardless of where it is installed, home or office...
Acquisitions - Winners and Losers on Dec 10, 2019
Most major manufacturers have been acquired over the last decade. But which have been good deals or not? In this report, we analyze the...
Bosch Budget 3000i Cameras Tested on Dec 05, 2019
Bosch has long had a hole in its lineup for, as it describes, "competitively-priced cameras". Now, Bosch has released its 3000i series cameras...
AVTech ~$70 IP Cameras Tested Vs Dahua and Hikvision on Dec 04, 2019
Taiwanese manufacturer Avtech is taking direct aim at low cost leaders Dahua and Hikvision with ~$70 starlight and white light illuminator...
Vunetrix Health Monitoring Company Profile on Nov 26, 2019
Vunetrix boasts that they make the integrators the 'HERO' by using Vunetrix's monitoring. We spoke to Vunetrix to better understand their...
Wyze AI Analytics Tested - Beats Axis and Hikvision, Now Improved, Now Being Terminated on Nov 25, 2019
When we originally tested Wyze's free person detection deep learning analytics in July 2019, they performed well, with few false alarms, but a long...
Top 2020 Trend - AI Analytics on Nov 22, 2019
170+ Integrators answered: What do you think will be the top industry trend in 2020? Why? For the 4th year in a row, AI/video analytics was...
Avigilon H4 Intercom Tested on Nov 20, 2019
Avigilon is well-known for video surveillance and access, but how well does the company's intercom work? We purchased and tested Avigilon's H4...
Hikvision Dual Lens Face Recognition Camera Tested on Nov 19, 2019
Hikvision's Dual Lens Facial Recognition camera, claims that it "adopts advanced deep learning algorithm and powerful GPU to realize instant face...

Most Recent Industry Reports

Video Surveillance 101 Course Opened on Dec 12, 2019
IPVM is adding a Video Surveillance 101 course, designed to help those new to the industry to quickly understand the most important terms,...
Verkada Notification Outage on Dec 12, 2019
Verkada is suffering an event notification outage and analytic search failures. Inside, we examine what the issues are, what Verkada told IPVM...
Hikvision DS 2nd Gen Intercom Tested on Dec 12, 2019
With its newest IP intercom, Hikvision proclaims users can 'get full control over an entrance' regardless of where it is installed, home or office...
Honeywell 30 Series Cameras Tested Vs Dahua and Hikvision on Dec 11, 2019
Honeywell has infamously OEMed Dahua and Hikvision for years, but now they have introduced an NDAA-compliant line, the 30 Series, claiming "lower...
"Good Market, Bad Business Models" - Residential Security on Dec 11, 2019
Industry banker John Mack, at his company's annual event, took aim squarely at the problems in the residential security...
IP Camera Browser Support: Who's Broken / Who Works on Dec 10, 2019
For many years, IP cameras depended on ActiveX control, whose security flaws have been known for more than a decade. The good news is that this is...
Acquisitions - Winners and Losers on Dec 10, 2019
Most major manufacturers have been acquired over the last decade. But which have been good deals or not? In this report, we analyze the...
IP Camera Installability Shootout 2019 - Avigilon, Axis, Bosch, Dahua, Hanwha, Hikvision, Uniview, Vivotek on Dec 09, 2019
What are the best and worst cameras to install? Which manufacturers make it the hardest or easiest to install their cameras? We tested 35 total...
Viisights Raises $10 Million, Behavior Analytics Company Profile on Dec 09, 2019
Viisights, an Israeli AI analytics startup marketing "Behavioral Understanding Systems", announced $10 million Series A funding. We spoke to...
Disruptor Wyze Releases Undisruptive Smartlock on Dec 06, 2019
While Wyze has disrupted the consumer IP camera market with ~$20 cameras, its entrance into smart locks is entirely undisruptive. We have...